sparkStreamming和高级数据源kafka

对于SparkStreaming+Kafka的组合，有两种方法。

Approach 1: Receiver-based Approach

Approach 2: Direct Approach (No Receivers)

实例1----KafkaReceive

----------------------------------------------------------前提---------------------------------------------------------------------------------

启动zookeeper集群

启动kafka集群

-------------------------------------------------------------------------------------------------------------------------------------------------

1、在kafka下创建一个“sparkStreamingOnKafkaReceive”的topic

root@master:/usr/local/kafka# bin/kafka-topics.sh --create --zookeeper master:2181,worker1:2181,worker2:2181 --replication-factor 2 --partitions 1 --topic sparkStreamingOnKafkaReceive 

2、启动這个topic的producer

 bin/kafka-console-producer.sh --broker-list master:9092,worker1:9092,worker2:9092 --topic sparkStreamingOnKafkaReceive

3、运行sparkStream程序，程序如下：

import org.apache.spark.streaming.kafka.KafkaUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.{SparkConf, SparkContext}
import scala.collection._

object streamingOnKafkaReceive {
  def main(args: Array[String]) {
    val conf = new SparkConf().setMaster("local[4]").setAppName("streamingOnKafkaReceive")
    val sc = new SparkContext(conf)
    val ssc = new StreamingContext(sc,Seconds(6))
    ssc.checkpoint("/Res")

    val topic = immutable.Map("sparkStreamingOnKafkaReceive" -> 2)
    val lines = KafkaUtils.createStream(ssc, "Master:2181,Worker1:2181,Worker2:2181","MyStreamingGroup",topic).map(_._2)

    val words  = lines.flatMap(_.split(" "))

    val wordCount = words.map(x => (x,1)).reduceByKey(_+_)

    wordCount.print()

    ssc.start()
    ssc.awaitTermination()
	}
}

4、随便输入一些字符串，运行结果

实列2----DirectStream

import kafka.serializer.StringDecoder

import org.apache.spark.streaming._
import org.apache.spark.streaming.kafka._
import org.apache.spark.SparkConf


object DirectKafkaWordCount {
  def main(args: Array[String]) {
    if (args.length < 2) {
      System.err.println(s"""
                            |Usage: DirectKafkaWordCount <brokers> <topics>
                            |  <brokers> is a list of one or more Kafka brokers
                            |  <topics> is a list of one or more kafka topics to consume from
                            |
        """.stripMargin)
      System.exit(1)
    }



    val Array(brokers, topics) = args

    // Create context with 2 second batch interval
    val sparkConf = new SparkConf().setAppName("DirectKafkaWordCount").setMaster("local[2]")
    val ssc = new StreamingContext(sparkConf, Seconds(2))

    // Create direct kafka stream with brokers and topics
    val topicsSet = topics.split(",").toSet
    val kafkaParams = Map[String, String]("metadata.broker.list" -> brokers)
    val messages = KafkaUtils.createDirectStream[String, String, StringDecoder, StringDecoder](
      ssc, kafkaParams, topicsSet)

    // Get the lines, split them into words, count the words and print
    val lines = messages.map(_._2)
    val words = lines.flatMap(_.split(" "))
    val wordCounts = words.map(x => (x, 1L)).reduceByKey(_ + _)
    wordCounts.print()

    // Start the computation
    ssc.start()
    ssc.awaitTermination()
  }
}
// scalastyle:on println